Home / Skills / get-prompt-from-image

get-prompt-from-image

Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references. Do not use for requests that only require OCR or an ordinary image description.

ScannedSkillSource: GitHub

5,800 stars +89 this week Updated 1mo ago License MIT Context ≈105 tokens always loaded

79popular

Why this score

Stars

24/35

Usage (forks)

10/15

Upkeep

20/25

License

15/15

Owner history

10/10

This repo hosts 2 skills, so its 5,800 stars are split between them (about 2,900 each) for scoring.

Popularity score: 79/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 20, 2026 at commit 9f8aa1a44a4a, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

Name	Score	Stars	Context	Updated
This oneget-prompt-from-image wuyoscar/GPT-Image2-Skill · Skill	79	★ 5.8k	≈105 always	1mo ago
image-analysis countbot-ai/CountBot · Skill Same job: documents & pdfs	68	★ 784	≈21 always	25d ago
nuyoah-xiezhen-prompt nuyoah-ai-works/nuyoah-xiezhen-prompt · Skill Both about prompt and image	69	★ 765	≈42 always	2mo ago
image axoviq-ai/synthadoc · Skill Both about image and extract	66	★ 1.6k	≈12 always	16d ago
image-generation zhayujie/CowAgent · Skill Both about image and generation	94	★ 47k	≈46 always	16d ago
sn-image-imitate OpenSenseNova/SenseNova-Skills · Skill Both about imitate and image	76	★ 5.8k	≈32 always	27d ago

Install

mkdir -p .claude/skills/get-prompt-from-image

curl -sL https://codeload.github.com/wuyoscar/GPT-Image2-Skill/tar.gz/9f8aa1a44a4a5c0f5a5d6e45eed564b3e2d5b87f | tar -xz -C .claude/skills/get-prompt-from-image --strip-components=3 "GPT-Image2-Skill-9f8aa1a44a4a5c0f5a5d6e45eed564b3e2d5b87f/skills/get-prompt-from-image"

To remove it later:

rm -rf .claude/skills/get-prompt-from-image

npx skills add wuyoscar/GPT-Image2-Skill --skill get-prompt-from-image

Pinned to commit 9f8aa1a44a4a as listed by GitHub.

Context cost: ≈105 tokens loaded every session (name and description), plus ≈1.8k tokens when the skill is used.

The Claude Code command downloads this skill folder at the pinned commit into .claude/skills/. The Skills CLI (npx skills) works with many agents but can't pin a version, so it installs whatever is current.

Used for

Operations › Documents & PDFs

Facts

Repo: wuyoscar/GPT-Image2-Skill
Stars: 5,800
Forks: 470
Last push: 2026-09-30 (1mo ago)
License: MIT
Owner: wuyoscar · since 2020
Language: Python
Works with: Claude Code, Skills CLI